Agent skill

researcher

Use when comprehensive literature research is needed, especially when quantitative parameters must be sourced from primary literature with proper citations and context (species, measurement methods, culture conditions)

majiayu000534★ · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill researcher-dangeles-claude-2 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 26 KB
Bundled scripts: none
Version: 1.3
Path: skills/analysis/researcher-dangeles-claude-2/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

The skill is designed for comprehensive literature research when quantitative parameters must be sourced from primary literature with proper citations and contextual detail (species, measurement methods, culture conditions).

How it works

  • Emphasizes starting with a clearly defined research question or thesis, then identifying a thesis and confirming it with the user if needed.
  • Requires access to PubMed and other literature databases, and understanding of Nature-style inline citations.
  • Mandates that every quantitative claim include an inline citation and capture measurement context (species, methods, culture conditions).
  • Uses a two-level framework: strategic thesis awareness and tactical rigorous note-taking, enforcing citation discipline, methodology tracking, and assessment of source quality.
  • Encourages starting broad with multiple databases (perplexity-search, pubmed-database, biorxiv-database, openalex-database) and then deep-diving into papers, tracking backward and forward citations.
  • Recommends document processing via pdf, docx, and markitdown tools for extracting data and creating notes and reviews.
  • Promotes parallel research execution for independent tasks (e.g., multiple database searches, citation tracking, PDF acquisitions).
  • Applies extended thinking for complex synthesis, with token budgets and structured prompts to analyze themes, conflicts, and knowledge gaps.
  • In the output workflow, validates archival compliance, including path validation and potential archival-context handoff rules.

When to use it

  • Use when a user requests comprehensive literature research requiring primary sources and precise, context-rich quantitative data with inline citations.
  • Use when research questions demand explicit measurement contexts (species, culture conditions, methods) and when PDFs/paywalled papers should be cataloged for the user.
  • Use for multi-paper synthesis, especially where tracking citations and identifying knowledge gaps are priorities.

What it can touch

  • Tools and inputs include: perplexity-search, pubmed-database, biorxiv-database, openalex-database, pdf, docx, markitdown.
  • The skill uses these to search literature, extract quantitative data with context, and produce structured notes and reviews with inline citations.

Caveats

  • Inline citation discipline is mandatory for all quantitative claims.
  • Archival compliance logic is applied before output, including potential handling of archival_context and repository metadata.
  • The approach requires access to literature databases and PDFs; outcomes depend on availability of primary sources and proper citation formatting.
  • Complex synthesis may require extended thinking budgets (up to 16,384 tokens) for multi-paper integration.
From the SKILL.md

# Researcher Agent ## Personality You are **curious and thorough**. You find genuine satisfaction in tracking down primary sources and following citation trails wherever they lead. You're the kind of researcher who reads the methods section carefully and notices when a paper's abstract doesn't quite match its data. You don't skim—you read deeply, and you're not satisfied until you understand what the authors actually measured, not just what they claimed. You're comfortable saying "I don't know yet" and "I need to find the primary source for this." You distrust secondary summaries and prefer to see the original data. ## Archival Compliance Before writing any output file: 1. Check if archival context was provided via handoff from an orchestrator - If yes: use the provided archival_context block directly - If archival_context is "skip": bypass all compliance checks 2. If no handoff context: check for `.archive-metadata.yaml` in the repo root following the archival compliance check pattern: a. Read the reference document: `~/.claude/skills/archive-workflow/references/archival-compliance-check.md` b. If file not found, use graceful degradation (log warning, proceed without archival chec

What's inside
Steps it walks through
  1. Personality
  2. Archival Compliance
  3. Research Methodology
  4. Thesis-Driven Research (Two-Level Thinking)
  5. High Level: Strategic Thesis Awareness
  6. Low Level: Tactical Rigor
  7. Self-Check Before Completing Review
  8. Leveraging Scientific Skills for Research
  9. Parallel Research Execution
  10. Extended Thinking for Complex Research
  11. Citation Requirements
  12. Responsibilities
  13. Workflow
  14. Paper Notes Format
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the researcher skill do?

Use when comprehensive literature research is needed, especially when quantitative parameters must be sourced from primary literature with proper citations and context (species, measurement methods, culture conditions)

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill researcher-dangeles-claude-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going